CN111638784B - Facial expression interaction method, interaction device and computer storage medium - Google Patents
Facial expression interaction method, interaction device and computer storage medium Download PDFInfo
- Publication number
- CN111638784B CN111638784B CN202010454095.XA CN202010454095A CN111638784B CN 111638784 B CN111638784 B CN 111638784B CN 202010454095 A CN202010454095 A CN 202010454095A CN 111638784 B CN111638784 B CN 111638784B
- Authority
- CN
- China
- Prior art keywords
- facial expression
- expression
- preset
- information
- image model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/174—Facial expression recognition
- G06V40/176—Dynamic expression
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Processing Or Creating Images (AREA)
Abstract
The application discloses a facial expression interaction method, an interaction device and a computer storage medium, wherein the facial expression interaction method comprises the following steps: loading a preset image model; acquiring a facial expression image of a user; extracting key point information of the facial expression image; and mapping the key point information to a preset image model so that the preset image model makes expressions corresponding to the key point information. By the method, the image model is driven by the expression change expressed based on the key points of the human face, and real-time, dynamic and interesting interactive experience is obtained.
Description
Technical Field
The present disclosure relates to the field of graphic image processing and computer vision technologies, and in particular, to a facial expression interaction method, an interaction device, and a computer storage medium.
Background
The expression interaction refers to a technology for driving a virtual character to make a corresponding expression by capturing the expression action of a human face in real time, and has wide application in occasions such as man-machine interaction virtual games, virtual person broadcasting, 3D film and television production and the like.
At present, a part of merchants can adopt artificial intelligence to realize the augmented reality effect, so that a vivid expression interaction scene is realized. The augmented reality refers to a technology of precisely calculating the position and angle of a camera image and adding a virtual image, so that the virtual world on a screen can be combined and interacted with a real world scene. As the technology of augmented reality is becoming more popular, its applications are also diversified. In various show exhibition scenes, the interactive experience effect of exhibition is further improved by the application of technologies such as artificial intelligence and augmented reality, but the combination of most of the current artificial intelligence technologies with the scenes and the exhibition contents is still in the basic effect superposition level, and real-time, dynamic and interesting interactive experience cannot be provided.
Disclosure of Invention
The application provides at least one facial expression interaction method, an interaction device and a computer storage medium.
The first aspect of the present application provides a facial expression interaction method, which includes:
loading a preset image model;
acquiring a facial expression image of a user;
extracting key point information of the facial expression image;
and mapping the key point information to the preset image model so that the preset image model makes the expression corresponding to the key point information.
By the method, the image model is driven based on the expression change expressed by the key points of the face, and real-time, dynamic and interesting interactive experience is obtained.
The step of mapping the key point information to the preset image model so that the preset image model makes the expression corresponding to the key point information comprises the following steps:
comparing the key point information differences according to the time sequence of the facial expression images of the continuous multiframes, so that the key point information is combined into facial expression information;
under the condition that the facial expression information is matched with preset basic expression information, mapping the facial expression information into the preset image model so that the preset image model makes an expression corresponding to the basic expression information; the preset basic expressions comprise at least one type, and each basic expression has corresponding basic expression information.
By the method, the key point changes in the facial expression images are compared, and the expressions of the preset image model are reflected by the position changes of the key points.
The step of comparing the key point information differences according to the time sequence of the facial expression images of the continuous multiframes so as to combine the key point information into facial expression information comprises the following steps:
dividing the key points into eyebrow region key points, eye region key points, nose region key points, mouth region key points and face contour key points according to the face region;
comparing the position change of key points in each face area according to the time sequence of the facial expression images of the continuous multiframes;
and combining the preset image model and the position change of the key points in each face area to obtain the facial expression information of each face area.
By the method, the face region is specifically divided into different regions, and the key points of the different regions represent the expression changes of the different regions.
The step of matching the facial expression information with preset basic expression information comprises the following steps:
comparing the corresponding relation between the key point information corresponding to the facial expression information and the key point information of each preset basic expression information, wherein the preset basic expression comprises at least one key point information;
and confirming the preset basic expression according to the comparison result.
The step of extracting key point information of the facial expression image comprises the following steps:
and identifying the facial expression image by using a preset neural network to obtain key point information corresponding to the preset number of key points in the facial expression image.
By the method, the key points are identified for the facial expression image through the preset neural network, and the detection precision is higher as the number of the key points is increased.
After the step of mapping the facial expression information to the preset image model so that the preset image model makes the expression corresponding to the basic expression information, the facial expression interaction method further comprises the following steps:
judging whether the basic expression corresponding to the facial expression information is a specific expression or not, wherein the specific expression is at least one of the basic expressions;
and when the basic expression corresponding to the facial expression information is the specific expression, displaying a preset animation corresponding to the preset image model and the specific expression.
Through the mode, a plurality of basic expressions are prestored in the database, and when the preset image model is successfully matched with the basic expressions, namely, the user makes the expressions identical to the basic expressions, the animation of the image model can be triggered, and the interestingness is improved.
The step of loading the preset image model comprises the following steps:
displaying all the image models in the database;
and selecting the preset image model based on user input information, or switching the currently displayed image model to the preset image model based on the user input information.
By the method, the three-dimensional virtual content, namely the image model, can be quickly replaced according to the requirements of users, and the system supports the image models of various artistic styles.
Wherein the preset image model is a three-dimensional image model; the facial expression interaction method further comprises the following steps:
extracting key point information and three-dimensional information of the facial expression images of continuous multiframes;
and mapping the key point information to the preset image model, and triggering the three-dimensional animation of the preset image model based on the three-dimensional information.
By the mode, on the basis of the plane expression interaction scene, the three-dimensional expression interaction scene is increased.
After the step of loading the preset image model, the facial expression interaction method further comprises the following steps:
acquiring an interactive image acquired by a camera;
and displaying the waiting animation of the preset image model under the condition that the face or the human body of the user is not detected from the interactive image.
After the step of loading the preset image model, the facial expression interaction method further comprises the following steps:
acquiring an interactive image acquired by a camera;
and under the condition that the face or the human body of the user is detected from the interactive image, acquiring the facial expression image of the user.
By the mode, when the user does not use the facial expression interaction function, the attention of the user is absorbed by playing the waiting animation.
The step of acquiring the facial expression image of the user under the condition that the face or the human body of the user is detected from the interactive image comprises the following steps:
judging whether the face or the human body of the user is in a preset area range of the interactive image and/or whether the size of the face or the human body of the user is larger than a preset size or not under the condition that the face or the human body of the user is detected from the interactive image;
if yes, acquiring the facial expression image of the user.
The step of acquiring the facial expression image of the user under the condition that the face or the human body of the user is detected from the interactive image comprises the following steps:
judging whether the face or the human body of the user is in a preset area range of the interactive image and/or whether the size of the face or the human body of the user is larger than a preset size or not under the condition that the face or the human body of the user is detected from the interactive image;
if not, displaying a prompt interface of the guide information.
By the method, the user is guided to adjust the position, so that a better facial expression image can be obtained.
A second aspect of the present application provides an interactive apparatus, the interactive apparatus comprising:
the loading module is used for loading a preset image model;
the extraction module is used for acquiring the facial expression image of the user and extracting key point information of the facial expression image;
and the expression module is used for mapping the key point information to the preset image model so that the preset image model can make expressions corresponding to the key point information.
A third aspect of the present application provides an interactive apparatus comprising a processor and a memory; the memory stores a computer program, and the processor is configured to execute the computer program to implement the steps of the facial expression interaction method.
A fourth aspect of the present application provides a computer storage medium, where the computer storage medium stores a computer program, and the computer program when executed implements the steps of the facial expression interaction method described above.
According to the scheme, the interaction device loads the preset image model; acquiring a facial expression image of a user; the key point information of the extracted facial expression image; and mapping the key point information to a preset image model so that the preset image model makes expressions corresponding to the key point information. By the method, the image model is driven by the expression change expressed based on the key points of the human face, and real-time, dynamic and interesting interactive experience is obtained.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort to those of ordinary skill in the art.
Fig. 1 is a flowchart of a first embodiment of a facial expression interaction method provided in the present application;
fig. 2 is a flowchart of a second embodiment of a facial expression interaction method provided in the present application;
fig. 3 is a flowchart of a third embodiment of a facial expression interaction method provided in the present application;
FIG. 4 is a schematic diagram of a facial expression interaction method provided by the present application;
FIG. 5 is a schematic structural diagram of an embodiment of an interactive apparatus provided in the present application;
FIG. 6 is a schematic structural diagram of another embodiment of an interactive apparatus provided in the present application;
fig. 7 is a schematic structural diagram of an embodiment of a computer storage medium provided in the present application.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the problem that the prior art cannot provide real-time, dynamic and interesting interaction experience, the application provides a facial expression interaction method, and by combining with facial key point detection, the facial actions of a user can be accurately restored in a virtual character in real time, and the user can make specific expression to trigger content interaction.
After the three-dimensional modeling is carried out on the images of related characters, animals and the like, the user drives the originally static image model through the change of the facial expression, so that real-time, dynamic and interesting interactive experience is obtained, and expression twinning is realized in a simple form of facial expression driving.
Referring to fig. 1 specifically, fig. 1 is a flowchart of a first embodiment of a facial expression interaction method provided in the present application. The facial expression interaction method is applied to an interaction device, and the interaction device can be specifically an exhibition and display product, an interaction group photo integrated machine, an interaction group photo mobile terminal, a multimedia decoration and display device and the like. In the application, the interaction device can be a 1080P LED display screen all-in-one machine or a picture frame display screen and the like, and the interaction device is provided with a 1080P camera. The camera is configured to capture the face, human body actions, gestures and the like of a user, and the interaction device is configured to display the group photo content in real time, instruct prompt and the like.
As shown in fig. 1, the facial expression interaction method of the present embodiment specifically includes the following steps:
s101: loading a preset image model.
Wherein, the interactive device carries people on the display screen and displays a preset image model. Classifying according to dimensions, wherein the preset image model can be a two-dimensional plane image model or a three-dimensional image model; classifying according to the image types, wherein the preset image model can be an animal image model, such as panda image, or a human image model, such as Van-Gao image, etc.
Specifically, the preset image model may be represented as a displayed product such as a museum, an art gallery, a science and technology gallery, a planning gallery, a city exhibition hall, etc., and may be represented as a decorative painting of a theme park, various theme galleries, a mall, and an indoor wall surface.
S102: and acquiring a facial expression image of the user.
The interaction device shoots a preset area through the carried camera, and acquires an interaction image aiming at the preset area. The interactive device detects whether the face or the human body of the user appears in the interactive image through an image detection technology. If the face or the human body of the user is detected from the interactive image, the camera is controlled to focus the face or the human body of the user, and the face expression images of the continuous multiframes are shot. If the face or the human body of the user cannot be detected from the interactive image, playing a waiting animation of a preset image model, and attracting the user through the interesting waiting interactive animation.
Further, for a multi-person scene, the interaction device can control the camera to acquire facial expression images of continuous multi-frames of tracking targets by taking the face or the human body closest to the center of the interaction image as the tracking target when detecting that the face or the human body appears in the interaction image.
S103: and extracting key point information of the facial expression image.
The interaction device marks key points in the facial expression images of the continuous multiframes based on the same marking rule, and key point information of the facial expression images is obtained. The keypoint information may specifically include the number of keypoints and the location of the keypoints.
In this embodiment, by increasing the number of key points marked by the interactive device, the recognition accuracy of the facial expression can be improved, for example, in this application, the interactive device can detect up to 240 facial key points through the face detection core technology, and the operation is efficient. In addition, the positions marked by the plurality of key points can be combined into the expression outline of the facial expression.
S104: and mapping the key point information to a preset image model so that the preset image model makes expressions corresponding to the key point information.
The interaction device maps the key point information acquired in step 103 to a preset image model. Specifically, the interaction device maps the expression profile formed by the key point information into a preset image model, so that the preset image model makes the same expression as the facial expression of the user, and the effect of facial expression interaction is achieved.
Specifically, the preset character model includes at least 52 basic expressions, that is, the preset basic expressions include at least one, and each basic expression has corresponding basic expression information. The interaction device controls the preset image model to make the matched basic expression under the condition that the expression profile formed by the key points is matched with the stored basic expression. In some possible embodiments, the interaction device may further compare a correspondence between a key point in the facial expression and a key point of each basic expression, and control the preset image model to make the basic expression when the key point of the facial expression is matched with a key point of a certain basic expression.
In this embodiment, the interaction device loads a preset image model; acquiring facial expression images of a user for a plurality of frames; extracting key point information of facial expression images of continuous multiframes; and mapping the key point information to a preset image model. By the method, the image model is driven by the expression change expressed based on the key points of the human face, and real-time, dynamic and interesting interactive experience is obtained.
On the basis of the facial expression interaction method in the above embodiment, another specific facial expression interaction method is further provided, referring specifically to fig. 2, and fig. 2 is a schematic flow chart of a second embodiment of the facial expression interaction method provided in the present application.
As shown in fig. 2, the facial expression interaction method of the embodiment specifically includes the following steps:
s201: and displaying the image model in the database.
The interaction device displays all the image models stored in the database on the display screen. To accommodate the screen size of the display screen, the visual model may be displayed in a thumbnail manner.
Further, the character models can classify all the character models into a plurality of areas or folders according to dimension classification and/or character type classification, and then the character models in a certain area or folder are specifically displayed according to the selection of the user.
S202: the preset character model is selected based on the user input information, or the currently displayed character model is switched to the preset character model based on the user input information.
The facial expression interaction system of the interaction device supports switching of different contents, namely different shape models, in the content library.
Specifically, the interaction device receives input information of clicking a certain image model on the display screen by a user, and loads the corresponding image model on the display screen based on the input information. By providing the image models of various types and various contents for the users, the user requirements of different age groups, different interest groups and the like can be met, and the user experience is improved.
Further, the facial expression interaction system of the interaction device also supports various artistic styles. When a user selects a certain character model, the interactive device can also provide a selection interface of different artistic styles of the character model. For example, when the user selects the "Van Gao" image model, the interaction means further provides different artistic styles, such as a canvas artistic style, a modern artistic style, a cartoon artistic style, etc., for the user to select. And after the user selects to finish, loading the interactive device into the image model.
S203: and acquiring a facial expression image of the user.
The interaction device shoots a preset area through the carried camera, and facial expression images aiming at the preset area are collected.
S204: and extracting key point information of the facial expression image.
The interaction device sequentially inputs the facial expression images of the continuous multiframes into the preset neural network according to the acquisition sequence. The preset neural network can output key points which can represent facial expressions in normal facial images through model training. The preset neural network of the application may be configured to output at least 240 face key points of each facial expression image.
The interactive device can mark facial features and contour positioning of the face by combining a key point detection technology with a millisecond-level face detection technology, and is mainly used for positioning the positions of key areas of the face, including eyebrows, eyes, nose, mouth, facial contours and the like. Under the camera preview model, the face detection technology can also support real-time face tracking with the minimum resolution of 40 x 40 and output key point information and face frame information. Meanwhile, technical support is provided for the conditions of multiple expressions (such as eye closure), large angles (such as side faces), dark/inverse/strong light, multiple people scenes, long-distance and small-part face shielding and the like.
S205: the key points are divided into eyebrow area key points, eye area key points, nose area key points, mouth area key points and face contour key points according to the face area.
The interaction device divides the face key points of each facial expression image into eye area key points, nose area key points, mouth area key points and face outline key points of the eyebrow area key points according to the same division rule. In some possible embodiments, the face key points may be further divided into other key points in other areas of the face, which will not be described herein. In general, if the number of marked key points is enough, the dense key points can also show the outline shape of the face component.
S206: and comparing the position change of the key points in each face area according to the time sequence of the facial expression images.
The interactive device compares the position change of key points in each face area according to the time sequence of the facial expression images of the continuous multiframes, so that the expression change in each face area is obtained.
Specifically, taking an eye area as an example, the interactive device compares the position change of the key points of the eye area in each frame of facial expression image according to the acquisition sequence, so that the change condition of eyes of a user, such as the expression of blinking, white-turning and the like of the user, can be obtained; taking a mouth area as an example, the interactive device compares the position change of key points of the mouth area in each frame of facial expression image according to the acquisition sequence, so that the change condition of the mouth of the user, such as the expression of flat mouth, smile (mouth lifting), laugh and the like of the user, can be obtained.
S207: and combining a preset image model and the position change of the key points in each face area to obtain the facial expression information of each face area.
The interaction device obtains the expression condition of each face area according to the position change of the key points in each face area, and then combines the expression conditions of all the face areas to obtain the facial expression information of the user.
S208: and mapping the facial expression information into a preset image model so that the preset image model makes a corresponding expression.
The interaction device maps the facial expression information acquired in step 207 to a preset image model. Specifically, the interaction device maps the facial expression information of the continuous multi-frame facial expression images into a preset image model so that the preset image model makes the same expression as the facial expression of the user, and the effect of facial expression interaction is achieved.
On the basis of the facial expression interaction method in the above embodiment, another specific facial expression interaction method is further provided in the present application, referring specifically to fig. 3 and fig. 4, fig. 3 is a schematic flow chart of a third embodiment of the facial expression interaction method provided in the present application, and fig. 4 is a schematic frame diagram of the facial expression interaction method provided in the present application.
As shown in fig. 3, the facial expression interaction method of the embodiment specifically includes the following steps:
s301: loading a preset image model.
In which, as in the first diagram of fig. 4, the interactive device loads and displays the preset character model on the display screen, and further, the waiting animation of the preset character model can be played.
S302: and acquiring a facial expression image of the user.
In the second diagram in fig. 4, the interaction device shoots a preset area through the carried camera, and acquires a facial expression image aiming at the preset area.
Specifically, after the interactive device detects the face or the human body of the user, judging whether the face or the human body of the user is in a preset area range of the camera acquisition area, for example, a central area of the camera acquisition area; or judging whether the sizes of the face and the human body of the user in the acquired interactive image are larger than the preset size. When the face of the user is in the preset area and the ratio of the face of the user in the interactive image is larger than the minimum ratio, the interactive device can acquire the better face expression image, and the interactive requirement can be met. Because the user station is far away from the camera, the facial expression images acquired by the interaction device cannot meet the interaction requirement, at the moment, the interaction device displays a prompt interface of guiding information on the display screen, and the guiding information can be text information or image information for prompting the user to get close.
S303: and extracting key point information and three-dimensional information of the facial expression image.
The camera carried by the interaction device can be a depth camera, and RGBD information of a user can be acquired. The interaction device acquires key point information and three-dimensional information from RGBD information. According to the embodiment, the three-dimensional information of the facial expression image is collected, and the action expressions such as the turning of the user are restored, so that the image model can simulate the user to display the three-dimensional animation.
S304: and mapping the key point information to a preset image model, and triggering the three-dimensional animation of the preset image model based on the three-dimensional information.
The interaction device triggers a three-dimensional animation of the preset avatar model based on the three-dimensional information, i.e. controls the preset avatar model to restore the current facial motion expression of the user, as shown in the third and fourth diagrams in fig. 4.
Optionally, the interaction device may also switch the interaction scene material based on the user input instruction, for example, the current interaction scene material is a panda figure model, and the interaction device may switch the panda figure model to a tiger figure model based on the user input instruction.
S305: judging whether the basic expression corresponding to the facial expression information is a specific expression, wherein the specific expression is at least one of the basic expressions.
In order to enrich the user experience of facial expression interaction, the interaction device can also match the basic expression of the preset image model, namely, the basic expression of the user with the specific expression of the database after controlling the preset image model to display the basic expression of the user so as to judge whether the basic expression corresponding to the facial expression information of the user is the specific expression or not. The database may store a plurality of specific expressions, wherein the specific expressions are at least one of basic expressions, and each preset expression is configured with a corresponding preset animation. If the basic expression corresponding to the facial expression information of the user is a specific expression, step S306 is entered.
S306: and displaying the preset animation corresponding to the preset image model and the specific expression.
When the basic expression made by the user is consistent with the specific expression of the database, the interaction device can trigger the preset animation of the preset image model besides driving the preset image model to display the facial expression, so that the display effect of the preset image model and the interaction experience of the user are enriched. For example, when the user makes a smiling basic expression, the interaction device can control the preset image model to make a dance motion, and positive image elements such as sun, rainbow and the like can be displayed on the display interface.
Further, as shown in fig. 4, after the facial expression interaction is completed, that is, the user leaves the acquisition area of the camera, when the interaction device cannot acquire the facial expression image, the interaction device resumes the default display, and plays the waiting animation of the preset image model.
In order to implement the facial expression interaction method of the above embodiment, the present application further provides an interaction device, and specifically referring to fig. 5, fig. 5 is a schematic structural diagram of an embodiment of the interaction device provided by the present application.
As shown in fig. 5, the interaction device 400 of the present embodiment includes:
the loading module 41: the method comprises the steps of loading a preset image model;
the extracting module 42 is configured to obtain a facial expression image of a user, and further is configured to extract key point information of the facial expression image;
and the expression module 43 is configured to map the key point information to the preset image model, so that the preset image model makes an expression corresponding to the key point information.
In order to implement the facial expression interaction method of the above embodiment, another interaction device is further provided, and referring to fig. 6, fig. 6 is a schematic structural diagram of another embodiment of the interaction device provided in the present application.
As shown in fig. 6, the interaction device 500 of the present embodiment includes a processor 51, a memory 52, an input/output device 53, and a bus 54.
The processor 51, the memory 52, and the input/output device 53 are respectively connected to the bus 54, where the memory 52 stores a computer program, and the processor 51 is configured to execute the computer program to implement the facial expression interaction method of the foregoing embodiment.
In the present embodiment, the processor 51 may also be referred to as a CPU (Central Processing Unit ). The processor 51 may be an integrated circuit chip with signal processing capabilities. Processor 51 may also be a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components. The processor 51 may also be a GPU (Graphics Processing Unit, graphics processor), also called a display core, a vision processor, a display chip, and is a microprocessor that is specially used for image computation on a personal computer, a workstation, a game machine, and some mobile devices (such as a tablet computer, a smart phone, etc.). The GPU is used for converting and driving display information required by a computer system, providing a line scanning signal for a display, controlling the correct display of the display, and is an important element for connecting the display and a personal computer mainboard and is also one of important equipment for 'man-machine conversation'. The display card is an important component in the host computer, and is very important for people who are engaged in professional graphic design to take on the task of outputting and displaying graphics. The general purpose processor may be a microprocessor or the processor 51 may be any conventional processor or the like.
The present application also provides a computer storage medium, as shown in fig. 7, where the computer storage medium 600 is used to store a computer program 61, and the computer program 61, when executed by a processor, is configured to implement a method as described in an embodiment of the facial expression interaction method of the present applicant.
The method referred to in the applicant's facial expression interaction method embodiment, when implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a device, such as a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all or part of the technical solution contributing to the prior art, or in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing description is only of embodiments of the present invention, and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and the drawings of the present invention or directly or indirectly applied to other related technical fields are included in the scope of the present invention.
Claims (12)
1. The facial expression interaction method is characterized by comprising the following steps of:
loading a preset image model;
acquiring a facial expression image of a user;
extracting key point information of the facial expression image;
mapping the key point information to the preset image model so that the preset image model makes an expression corresponding to the key point information;
the step of mapping the key point information to the preset image model so that the preset image model makes the expression corresponding to the key point information comprises the following steps:
comparing the key point information differences according to the time sequence of the facial expression images of the continuous multiframes, so that the key point information is combined into facial expression information;
under the condition that the facial expression information is matched with preset basic expression information, mapping the facial expression information into the preset image model so that the preset image model makes an expression corresponding to the basic expression information; the preset basic expressions comprise at least one type, and each basic expression has corresponding basic expression information;
after the step of mapping the facial expression information to the preset image model so that the preset image model makes the expression corresponding to the basic expression information, the facial expression interaction method further comprises the following steps:
judging whether a basic expression corresponding to the facial expression information is a specific expression or not, wherein the specific expression is at least one of the basic expressions;
when the basic expression corresponding to the facial expression information is the specific expression, displaying a preset animation corresponding to the preset image model and the specific expression;
the preset image model is a three-dimensional image model; the facial expression interaction method further comprises the following steps:
extracting key point information and three-dimensional information of the facial expression images of continuous multiframes;
and mapping the key point information to the preset image model, and triggering the three-dimensional animation of the preset image model based on the three-dimensional information.
2. The facial expression interaction method according to claim 1, wherein,
the step of comparing the key point information differences according to the time sequence of the facial expression images of the continuous multiframes, thereby combining the key point information into facial expression information, comprises the following steps:
dividing the key points into eyebrow region key points, eye region key points, nose region key points, mouth region key points and face contour key points according to the face region;
comparing the position change of key points in each face area according to the time sequence of the facial expression images of the continuous multiframes;
and combining the preset image model and the position change of the key points in each face area to obtain the facial expression information of each face area.
3. The facial expression interaction method according to claim 2, wherein,
the step of matching the facial expression information with preset basic expression information comprises the following steps:
comparing the corresponding relation between the key point information corresponding to the facial expression information and the key point information of each preset basic expression information, wherein the preset basic expression comprises at least one key point information;
and confirming the preset basic expression according to the comparison result.
4. The facial expression interaction method according to claim 2, wherein,
the step of extracting key point information of the facial expression image comprises the following steps:
and identifying the facial expression image by using a preset neural network to obtain key point information corresponding to the preset number of key points in the facial expression image.
5. The facial expression interaction method according to claim 1, wherein,
the step of loading the preset image model comprises the following steps:
displaying all the image models in the database;
and selecting the preset image model based on user input information, or switching the currently displayed image model to the preset image model based on the user input information.
6. The facial expression interaction method according to claim 1, wherein,
after the step of loading the preset image model, the facial expression interaction method further comprises the following steps:
acquiring an interactive image acquired by a camera;
and displaying the waiting animation of the preset image model under the condition that the face or the human body of the user is not detected from the interactive image.
7. The facial expression interaction method according to claim 1, wherein,
after the step of loading the preset image model, the facial expression interaction method further comprises the following steps:
acquiring an interactive image acquired by a camera;
and under the condition that the face or the human body of the user is detected from the interactive image, acquiring the facial expression image of the user.
8. The facial expression interaction method according to claim 7, wherein,
the step of acquiring the facial expression image of the user under the condition that the face or the human body of the user is detected from the interactive image comprises the following steps:
judging whether the face or the human body of the user is in a preset area range of the interactive image and/or whether the size of the face or the human body of the user is larger than a preset size or not under the condition that the face or the human body of the user is detected from the interactive image;
if yes, acquiring the facial expression image of the user.
9. The facial expression interaction method according to claim 7, wherein,
the step of acquiring the facial expression image of the user under the condition that the face or the human body of the user is detected from the interactive image comprises the following steps:
judging whether the face or the human body of the user is in a preset area range of the interactive image and/or whether the size of the face or the human body of the user is larger than a preset size or not under the condition that the face or the human body of the user is detected from the interactive image;
if not, displaying a prompt interface of the guide information.
10. An interactive apparatus, characterized in that the interactive apparatus comprises:
the loading module is used for loading a preset image model;
the extraction module is used for acquiring the facial expression image of the user and extracting key point information of the facial expression image;
the expression module is used for mapping the key point information to the preset image model so that the preset image model can make an expression corresponding to the key point information;
the expression module is further used for comparing the key point information differences according to the time sequence of the facial expression images of the continuous multiframes, so that the key point information is combined into facial expression information; under the condition that the facial expression information is matched with preset basic expression information, mapping the facial expression information into the preset image model so that the preset image model makes an expression corresponding to the basic expression information; the preset basic expressions comprise at least one type, and each basic expression has corresponding basic expression information;
the expression module is further configured to determine whether a basic expression corresponding to the facial expression information is a specific expression, where the specific expression is at least one of the basic expressions;
when the basic expression corresponding to the facial expression information is the specific expression, displaying a preset animation corresponding to the preset image model and the specific expression;
the preset image model is a three-dimensional image model, and the expression module is also used for extracting key point information and three-dimensional information of the facial expression images of continuous multiframes; and mapping the key point information to the preset image model, and triggering the three-dimensional animation of the preset image model based on the three-dimensional information.
11. An interactive apparatus, characterized in that the interactive apparatus comprises a processor and a memory; the memory stores a computer program, and the processor is configured to execute the computer program to implement the steps of the facial expression interaction method according to any one of claims 1 to 9.
12. A computer storage medium, characterized in that the computer storage medium stores a computer program which, when executed, implements the steps of the facial expression interaction method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010454095.XA CN111638784B (en) | 2020-05-26 | 2020-05-26 | Facial expression interaction method, interaction device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010454095.XA CN111638784B (en) | 2020-05-26 | 2020-05-26 | Facial expression interaction method, interaction device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111638784A CN111638784A (en) | 2020-09-08 |
| CN111638784B true CN111638784B (en) | 2023-07-18 |
Family
ID=72332768
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010454095.XA Active CN111638784B (en) | 2020-05-26 | 2020-05-26 | Facial expression interaction method, interaction device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111638784B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749357B (en) * | 2020-09-15 | 2024-02-06 | 腾讯科技（深圳）有限公司 | Interaction method and device based on shared content and computer equipment |
| CN112652041B (en) * | 2020-12-18 | 2024-04-02 | 北京大米科技有限公司 | Virtual image generation method and device, storage medium and electronic equipment |
| CN112767520A (en) * | 2021-01-07 | 2021-05-07 | 深圳追一科技有限公司 | Digital human generation method and device, electronic equipment and storage medium |
| CN113989925A (en) * | 2021-10-22 | 2022-01-28 | 支付宝(杭州)信息技术有限公司 | Face brushing interaction method and device |
| CN114779948B (en) * | 2022-06-20 | 2022-10-11 | 广东咏声动漫股份有限公司 | Method, device and equipment for controlling instant interaction of animation characters based on facial recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018103220A1 (en) * | 2016-12-09 | 2018-06-14 | 武汉斗鱼网络科技有限公司 | Image processing method and device |
| CN109857311A (en) * | 2019-02-14 | 2019-06-07 | 北京达佳互联信息技术有限公司 | Generate method, apparatus, terminal and the storage medium of human face three-dimensional model |
| US10529113B1 (en) * | 2019-01-04 | 2020-01-07 | Facebook Technologies, Llc | Generating graphical representation of facial expressions of a user wearing a head mounted display accounting for previously captured images of the user's facial expressions |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190205627A1 (en) * | 2017-12-28 | 2019-07-04 | Facebook, Inc. | Systems and methods for generating amplified facial expressions based on facial recognition |
| CN109147017A (en) * | 2018-08-28 | 2019-01-04 | 百度在线网络技术（北京）有限公司 | Dynamic image generation method, device, equipment and storage medium |
| US20200090392A1 (en) * | 2018-09-19 | 2020-03-19 | XRSpace CO., LTD. | Method of Facial Expression Generation with Data Fusion |
| CN109829965B (en) * | 2019-02-27 | 2023-06-27 | Oppo广东移动通信有限公司 | Action processing method and device of face model, storage medium and electronic equipment |
| CN110363079A (en) * | 2019-06-05 | 2019-10-22 | 平安科技（深圳）有限公司 | Expression exchange method, device, computer installation and computer readable storage medium |
| CN110568933A (en) * | 2019-09-16 | 2019-12-13 | 深圳市趣创科技有限公司 | human-computer interaction method and device based on face recognition and computer equipment |
-
2020
- 2020-05-26 CN CN202010454095.XA patent/CN111638784B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018103220A1 (en) * | 2016-12-09 | 2018-06-14 | 武汉斗鱼网络科技有限公司 | Image processing method and device |
| US10529113B1 (en) * | 2019-01-04 | 2020-01-07 | Facebook Technologies, Llc | Generating graphical representation of facial expressions of a user wearing a head mounted display accounting for previously captured images of the user's facial expressions |
| CN109857311A (en) * | 2019-02-14 | 2019-06-07 | 北京达佳互联信息技术有限公司 | Generate method, apparatus, terminal and the storage medium of human face three-dimensional model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111638784A (en) | 2020-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111638784B (en) | Facial expression interaction method, interaction device and computer storage medium | |
| US11094131B2 (en) | Augmented reality apparatus and method | |
| CN112348969B (en) | Display method and device in augmented reality scene, electronic equipment and storage medium | |
| WO2022001593A1 (en) | Video generation method and apparatus, storage medium and computer device | |
| CN106803057B (en) | Image information processing method and device | |
| US8908904B2 (en) | Method and system for make-up simulation on portable devices having digital cameras | |
| EP2993893B1 (en) | Method for image segmentation | |
| US20100079491A1 (en) | Image compositing apparatus and method of controlling same | |
| US20210345016A1 (en) | Computer vision based extraction and overlay for instructional augmented reality | |
| CN106203286B (en) | Augmented reality content acquisition method and device and mobile terminal | |
| CN105404392A (en) | Monocular camera based virtual wearing method and system | |
| CN104508680B (en) | Improved video signal is tracked | |
| JP2022166078A (en) | Composing and realizing viewer's interaction with digital media | |
| KR20140082610A (en) | Method and apaaratus for augmented exhibition contents in portable terminal | |
| CN114363689B (en) | Live broadcast control method and device, storage medium and electronic equipment | |
| CN111667588A (en) | Person image processing method, person image processing device, AR device and storage medium | |
| CN111640192A (en) | Scene image processing method and device, AR device and storage medium | |
| WO2024001095A1 (en) | Facial expression recognition method, terminal device and storage medium | |
| CN111625100A (en) | Method and device for presenting picture content, computer equipment and storage medium | |
| CN113709545A (en) | Video processing method and device, computer equipment and storage medium | |
| CN111639613A (en) | Augmented reality AR special effect generation method and device and electronic equipment | |
| CN111627115A (en) | Interactive group photo method and device, interactive device and computer storage medium | |
| CN117333645A (en) | Annular holographic interaction system and equipment thereof | |
| US20080122867A1 (en) | Method for displaying expressional image | |
| CN114026524B (en) | Method, system, and computer-readable medium for animating a face |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |